This project focused on the analysis of digital network traffic patterns and prediction of online network traffic flows.
MedNition Inc., a Silicon Valley-based healthcare technology company applies machine learning to provide physicians and clinical practitioners with real-time clinical decision support to improve patient safety and improve operational efficiency for hospitals. With a predictive model that is clinically validated by teams of physicians, MedNition’s initial prototype product achieved medical device level accuracy which is required for clinical environments. MedNition’s simple deployment, HIPAA-compliancy and seamless integration into their customers existing medical record systems mean that physicians can start using MedNition instantly and without the need for time-consuming training or patient care workflow changes. Digamma’s team was involved from the beginning in the design and implementation of MedNition’s machine learning framework. Digamma’s team was involved from the beginning in the design and implementation of MedNition’s machine learning framework.
- Worked with diverse anonymized patient data — including nurse and physicians’ notes, patient medical history and vital measurements — provided in a variety of formats from several hospitals
- Used a variety of medical information ontologies and implemented feature engineering
- Applied state-of-the-art machine learning methods to predict the severity and risk of patients’ conditions
- Fine tuned algorithms to achieve a desired balance between precision and recall accuracy measures
Digamma’s team analyzed patients’ data at MedNition and played a key role in setting up the company’s machine learning-driven framework.